Advertisement

Survey on the Image Segmentation Algorithms

Conference paper
Part of the Springer Series in Geomechanics and Geoengineering book series (SSGG)

Abstract

Image segmentation techniques are always difficult and are the key point of image processing. Currently, many image segmentation algorithms are springing up, but there are no universal methods. Firstly, this paper analyses basic theory and advantages and disadvantages of traditional methods in the field of image segmentation, including threshold methods, edge detection methods, and region segmentation methods. Secondly, based on the evolution of traditional methods and new methods, which include the gene method, the research status of image segmentation algorithms in recent years is combined systematically and commented. Finally, the development trends and the difficulty of image segmentation are pointed out and, importantly, one new idea which is of significance is put forward.

Keywords

Image segmentation Threshold methods Edge detection Region segmentation Machine learning 

Notes

Acknowledgements

Thanks for support from Science and Technology Department of Shaanxi province [ Key technique research on petroleum steel pipes welt automatic detection based on DR images (2016GY-106) ], social science foundation of Shaanxi province [Strategy research on information construction of Shaanxi province oil and gas resource enterprises (15JZ047)] and key laboratory research plan of Shaanxi province department  [Research on oil and gas resource enterprises information construction in big data time (2015R026)].

References

  1. 1.
    Otsu N (1975) A threshold selection method from level histograms. Automatic 11(285–296):23–27Google Scholar
  2. 2.
    Liao M (2016) Watershed image segmentation algorithm based on morphological reconstruction. Sci Technol Forum 9Google Scholar
  3. 3.
    Zhang YF (2016) Improved watershed image segmentation algorithm [J]. Electron Technol Software Eng 5:109Google Scholar
  4. 4.
    Ng HF (2006) Automatic thresholding for defect detection. Pattern Recogn Lett 27(14):1644–1649CrossRefGoogle Scholar
  5. 5.
    Fan JL, Lei B (2012) A modified valley-emphasis method for automatic thresholding. Pattern Recogn Lett 33(6):703–708CrossRefGoogle Scholar
  6. 6.
    Shen XJ (2016) Fast recursive multi-thresholding algorithm. Jilin Univ J 46(2):528–534Google Scholar
  7. 7.
    Qiu LJ (2015) One automatic image threshold detection method based on gray histogram. Geospatial Inf 13(6):115–117Google Scholar
  8. 8.
    Liu JZ, Li WQ (1993) Two-dimension Otsu automatic threshold segmentation method of gray image. Acta Automatic Sinica 19(1):101–105Google Scholar
  9. 9.
    Abutaleb AS (1989) Automatic thresholding of gray -level picture using two -dimensional entropies. Pattern Recogn 47:22–32Google Scholar
  10. 10.
    Yuan J, Cheng GT (2016) Rapid OTSU method based on two-dimensional histogram of double slope. Appl Comput Res 33Google Scholar
  11. 11.
    Qian WX (2016) The improvement of the implementation method of the two-dimensional Otsu histogram oblique fast algorithm. J Huaqiao Univ (Nat Sci) 37(1)Google Scholar
  12. 12.
    Hong T (2016) Research on image segmentation based on OTSU algorithm and GA. J Liaoning Univ Technol (Nat Sci Ed). 36(2):99–102Google Scholar
  13. 13.
    Zhou D (2016) An improved Otsu threshold segmentation algorithm. J China Univ Metrol 27(3):319–323Google Scholar
  14. 14.
    Yan F (2014) Proficient in classical image processing algorithms. Beijing University of Aeronautics and Astronautics Press, Beijing, p 4Google Scholar
  15. 15.
    Wang D (2012) Image edge detection based on multi-granularity rough fuzzy set. PR AI 25(2):195–204Google Scholar
  16. 16.
    Hao HZ (2015) Noise image edge detection algorithm based on wavelet transform. JiSuanJI Yu XianDaiHua 2:80–85Google Scholar
  17. 17.
    Cui LQ (2016) Fusion of double threshold and improved morphological edge detection. Comput Eng Appl 5:1–4Google Scholar
  18. 18.
    Tian LP (2016) Image segmentation algorithm research based on threshold and graph theory. J Ningde Normal Univ (Nat Sci) 28(1):62–65Google Scholar
  19. 19.
    Wu QH (2016) Image segmentation algorithm based on graph theory and FCM. Chin J Liquid Displays 31(1):112–116CrossRefGoogle Scholar
  20. 20.
    Liu HP (2016) A normalized cut image segmentation method based on morphological watersheds. Electron Sci Tech 31(1):12–14Google Scholar
  21. 21.
    Ye Q (2016) Key techniques of image segmentation based on graph theory. Comput Digital Eng 8Google Scholar
  22. 22.
    Wang M (2011) Image segmentation algorithm based on edge detection and automatic seed region growing. J Xi’an Univ Post Telecommun 16(6):16–19CrossRefGoogle Scholar
  23. 23.
    Wu MY (2016) Object segmentation of infrared image based on hough transform. J Commun Univ China (Sci Technol) 23(4):20–26Google Scholar
  24. 24.
    Dunn JC (1973) A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters. J Cybern 3(3):32–57MathSciNetCrossRefGoogle Scholar
  25. 25.
    Guo XJ (2015) The application of K-means clustering algorithm in image segmentation. J Jilin Jianzhu Univ 32(6):63–66Google Scholar
  26. 26.
    Zhou SB (2010) New method for determining optimal number of clusters in K-means clustering algorithm. Comput Eng Appl 46(16):27–31Google Scholar
  27. 27.
    Wang JD (2016) Self-adaptive K-means on the method of image segmentation. Navig Position Timing 3(5):66–69Google Scholar
  28. 28.
    Zhang HZ (2009) Improved fuzzy means clustering algorithm based on selecting initial clustering centers. Comput Sci 36(6):206–209Google Scholar
  29. 29.
    Xu XZ (2010) New theories and methods of image segmentation. Acta Electron Sinica 2A:76–81Google Scholar
  30. 30.
    Zhang YQ (2011) image segmentation based on genetic neural network. Comput Design Appl 24(2):16–18Google Scholar
  31. 31.
    Guo XG (2016) Application of improved genetic algorithm in image segmentation. Instrum Technol 2:23–25Google Scholar
  32. 32.
    Liu GH (2016) Otsu image threshold segmentation method based on improved particle swarm optimization. Comput Sci 43(3):309–311Google Scholar
  33. 33.
    Liu ZY (2016) Image segmentation on genetic simulated annealing algorithm. Video Eng 40(8):15–18Google Scholar
  34. 34.
    Wang YC (2011) Study on image segmentation methods based on transition region. Dalian Maritime University, p 5Google Scholar
  35. 35.
    Pal NR, Pal SK (1993) A review on image segmentation techniques. Pattern Recogn 26(9):1277–1294CrossRefGoogle Scholar
  36. 36.
    Feng W (2011) Evaluation of several typical edge detection oprators. Electronic Design Eng 19(4):131–133Google Scholar
  37. 37.
    Zhang DF (2012) Matlab digital image process. China Machine Press, Beijing, p 1Google Scholar
  38. 38.
    Jiang H (2011) Self-adaption Canny edge detection based on subareas. Sci Technol Innov Newspaper 28:10Google Scholar
  39. 39.
    Zhao JT (2016) Line extraction method based on Harris algorithm. Electron Technol Software Eng 5Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Economy and Management CollegeXi’an Shiyou UniversityXi’anChina

Personalised recommendations